Sampling bias
Topic of Studies, data, and evidence, part of Data analysis
Sampling bias
| Type | Topic |
| Taught in | Studies, data, and evidence |
| Part | Data analysis |
| Questions using it | 2 |
A systematic difference between a sample and the population it is meant to represent, caused by the way units were chosen. Convenience and self-selected samples are the usual sources. A larger biased sample is not a better one: the bias does not shrink with n.
In Studies, data, and evidence
Many data are collected in ways far from random. A convenience sample takes whoever is available, and generalises only if the available units resemble the population. A self-selected sample takes whoever chooses to take part, as in a television phone-in poll; it rarely represents even the show’s viewers, and a keen caller may vote twice. In both, units are not sampled independently with equal probability, which biases estimates, and a larger sample of the same kind does not remove the bias.
Used in
- Taught in Studies, data, and evidence
- Also used in Classification trees
- Questions that use it (2) — Separate tuning from evaluation (answer) · What an accuracy table does and does not say (answer)
- All 6 questions on Studies, data, and evidence
See also
Observational study · Designed experiment · Randomised controlled trial · Confounding variable · Blinding and placebo · Simple random sample · Stratified and cluster sampling · A model for the sample